Conversational Finance Question Answering
ConvFinQA is a dataset designed to study the chain of numerical reasoning in conversational question answering. The dataset contains 3892 conversations containing 14115 questions where 2715 of the conversations are simple conversations, and the rest 1,177 are hybrid conversations.
Source: ConvFinQA: Exploring the Chain of Numerical Reasoning in
Conversational Finance Question Answering
Image Source: https://arxiv.org/pdf/2210.03849.pdf
Variants: ConvFinQA
This dataset is used in 2 benchmarks:
| Task | Model | Paper | Date |
|---|---|---|---|
| Question Answering | GPT-4 (8k) | Are ChatGPT and GPT-4 General-Purpose … | 2023-05-10 |
| Question Answering | General Crowd | Are ChatGPT and GPT-4 General-Purpose … | 2023-05-10 |
| Conversational Question Answering | APOLLO | APOLLO: An Optimized Training Approach … | 2022-12-14 |
| Question Answering | FinQANet (RoBERTa-large) | ConvFinQA: Exploring the Chain of … | 2022-10-07 |
| Conversational Question Answering | FinQANet (RoBERTa-large) | ConvFinQA: Exploring the Chain of … | 2022-10-07 |
Recent papers with results on this dataset: